13 papers
Recommendation Retrievers Need Verifiers: Universal Generative Reranking for Sequential Recommendations
Benyu Zhang, Qiang Zhang, Rui Li +3
First-stage recommenders in multi-stage systems produce a ranked candidate list from which a limited prefix is forwarded to downstream rankers. Because each forwarded item must be…
Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall
Jacqueline He, Howard Yen, Shuyue Stella Li +9
Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervision from stronger teachers, but whether its benefits are consistent across traini…
OneVLA: A Unified Framework for Embodied Tasks
Lingfeng Zhang, Xiaoshuai Hao, Yingbo Tang +10
Navigation and manipulation are fundamental capabilities of embodied intelligence, enabling robots to interpret natural language commands and interact physically with their surroun…
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
Jiarui Feng, Hanqing Zeng, Karish Grover +11
Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performa…
TARo: Token-level Adaptive Routing for LLM Test-time Alignment
Arushi Rai, Qiang Zhang, Hanqing Zeng +5
Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer…
VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
Qiuchen Wang, Shihang Wang, Yu Zeng +9
Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retrieval-augmented Generation (RAG) metho…
Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation
Benyu Zhang, Qiang Zhang, Jianpeng Cheng +10
Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are cr…
Efficient Sequential Recommendation for Long Term User Interest Via Personalization
Qiang Zhang, Hanchao Yu, Ivan Ji +14
Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for seque…
Exploring System 1 and 2 communication for latent reasoning in LLMs
Julian Coda-Forno, Zhuokai Zhao, Qiang Zhang +6
Should LLM reasoning live in a separate module, or within a single model's forward pass and representational space? We study dual-architecture latent reasoning, where a fluent Base…
Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-Head Decoding
Yunkai Zhang, Qiang Zhang, Feng Lin +7
Optimizing recommender systems for objectives beyond accuracy, such as diversity, novelty, and personalization, is crucial for long-term user satisfaction. To this end, industrial…
RecoWorld: Building Simulated Environments for Agentic Recommender Systems
Fei Liu, Xinyu Lin, Hanchao Yu +12
We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems. Such environments give agents a proper training space where they can…
GEM: Empowering LLM for both Embedding Generation and Language Understanding
Caojin Zhang, Qiang Zhang, Ke Li +6
Large decoder-only language models (LLMs) have achieved remarkable success in generation and reasoning tasks, where they generate text responses given instructions. However, many a…
S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
Hanqing Zeng, Yinglong Xia, Zhuokai Zhao +7
Fine-tuning pre-trained large language models (LLMs) presents a dual challenge of balancing parameter efficiency and model capacity. Existing methods like low-rank adaptations (LoR…